Anthropic on Vonnghttps://vonng.com/en/tags/anthropic/Recent content in Anthropic on VonngHugo -- gohugo.ioenrh@vonng.com (Ruohang Feng)rh@vonng.com (Ruohang Feng)© 2025 Ruohang FengSat, 04 Apr 2026 00:00:00 +0000LLMs Have Emotions: Claude's Internals Reveal Steerable 'Emotion Vectors'https://vonng.com/en/ai/ai-emotion/Sat, 04 Apr 2026 00:00:00 +0000rh@vonng.com (Ruohang Feng)https://vonng.com/en/ai/ai-emotion/Anthropic’s new research gives us the first direct look at causally steerable “emotion vectors” inside a large language model. That should change how we think about AI.